tensorflow / tensorflow/probability
Status of tfp.experimental.tangent_spaces
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 4.4k
- Forks
- 1.1k
- PR merge metrics
- No merged PRs in 30d
Description
When I use a TransformedDistribution with base SphericalUniform, I get incorrect densities. This is because the Bijector is applied to a manifold of strictly-lower intrinsic dimension than the space it is embedded in. (This is called the base measure problem.) Looking for a solution, I came across the following in the documentation:
- tfp.experimental.tangent_spaces
- tfd.Distribution.experimental_local_measure
- tfb.Bijector.experimental_compute_density_correction
These solve the problem by passing around a TangentSpace along with the point. I was wondering what the status of these components is, and whether there are any plans to add them to distributions like SphericalUniform.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the linked documentation for tfp.experimental.tangent_spaces, Distribution.experimental_local_measure, and Bijector.experimental_compute_density_correction. Compare their documented status with the SphericalUniform and TransformedDistribution behavior; done would require a decided path for supporting tangent-space-aware densities, including whether SphericalUniform should expose it.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100